1 / 3
Swipe to compare

Gemini 2.5 Flash is Google's workhorse reasoning model, designed for fast, high-quality responses across coding, mathematics, and scientific tasks. It features built-in "thinking" capabilities with configurable thinking levels, allowing it to balance response speed and reasoning depth based on task complexity. Supporting a 1M-token context window with multimodal inputs including text, images, audio, video, and PDFs, it delivers strong performance at a fraction of the cost and latency of larger Gemini Pro models.

Author
GoogleGoogle
Release Date
2025-06-17
Knowledge Cutoff
2025-01-31
License
Proprietary
I/O Format
Context Length
1.0M / 66K
API I/O (1M)
$0.3 / $2.5
How to Use
API Access
Output Speed
213 tok/s
Arena Overall
1411
Intelligence Index
27.0
Coding Index
22.2
Math Index
73.3
LiveBench
46.9
ForecastBench
58.5
GPQA Diamond
79.0%
HLE
11.1%
MMLU-Pro
83.2%
AIME 2025
73.3%
MATH-500
98.1%
LB Reasoning
44.6
LB Math
68.8
LB Data Analysis
47.3
LiveCodeBench
69.5%
LB Coding
66.0
LB Agentic
16.7
TAU2
31.6%
TerminalBench
13.6%
SciCode
39.4%
IFBench
50.3%
AA-LCR
0.6
Hallucination (HHEM)
7.8%
Factual Consistency (HHEM)
92.2%
LB Language
62.3
LB Instruction Following
28.5